基于联合方法的中文语义角色标注  

Chinese Semantic Role Labeling Basing on Combination Strategy

作　　者：王文学[1] 李芳[1] 

机构地区：[1]上海交通大学计算机科学与工程系,上海200240

出　　处：《小型微型计算机系统》2011年第11期2315-2319,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(60873134)资助

摘　　要：目前基于机器学习的中文语义角色标注(Semantic Role Labeling,SRL)方法大致可以分为两类:基于深层句法分析的方法和基于浅层句法分析的方法.由于基于这两种方法的SRL系统在性能和健壮性上各有优缺点,本文试图联合基于这两种方法的SRL系统的输出,通过一些全局特征训练出联合模型,对候选角色进行过滤,然后解决不满足句子论元结构限制的冲突角色得到最终标注结果,来提高标注的性能.在Chinese PropBank 1.0语料集上,联合模型的F值达到了78.41%,在基于深层句法分析的SRL的F值67.34%和基于浅层句法分析的SRL的F值71.67%基础上有了显著的提高,从而证明我们的联合方法是非常有效的.At present, Chinese semantic role labeling （SRL） systems based on machine learning can be categorized to full parsing based SRL and shallow parsing based SRL, generally. Considering that these two systems have advantage and weakness on performance and robustness respectively, this paper attempts to combine the outputs of these two systems, uses some global features to train combination model for filtering candidate arguments, then resolves roles violating domain knowledge constraints to obtain the final solution to improve performance of labeling. We report the experiments on Chinese PropBank { CPB ） 1.0. the F-Score of our combination system reaches 78.41%, Significantly improves performance on the basis of the F-Score（67.34% ） of full parsing based system and the F-Score{71.67% ） of shallow parsing based system, it is proved that our combination method is effective.

关 键 词：语义角色标注 深层句法分析 浅层句法分析 CHINESE PropBank SVM 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]